Physics Reasoning on MMLU-Pro Physics
88.5AccuracySC
Evaluation Results
| Method | Links | |
|---|---|---|
| SCBackbone=Qwen3-30B-Instruct, Inference Strategy=SC2026.07 | 88.5 | |
| MILESBackbone=Qwen3-30B-Instruct, Inference Strategy=MILES2026.07 | 88.5 | |
| MILESBackbone=GPT-OSS-20B, Inference Strategy=MILES2026.07 | 87 | |
| ZS-CoTBackbone=Qwen3-30B-Instruct, Inference Strategy=ZS-CoT2026.07 | 87 | |
| SCBackbone=GPT-OSS-20B, Inference Strategy=SC2026.07 | 86.5 | |
| BoTBackbone=Qwen3-30B-Instruct, Inference Strategy=BoT2026.07 | 86 | |
| ZS-CoTBackbone=GPT-OSS-20B, Inference Strategy=ZS-CoT2026.07 | 85.5 | |
| MILESBackbone=GPT-4.1-mini, Inference Strategy=MILES2026.07 | 85 | |
| MILESBackbone=GPT-4.1, Inference Strategy=MILES2026.07 | 84.5 | |
| BoTBackbone=GPT-4.1, Inference Strategy=BoT2026.07 | 84 | |
| SCBackbone=GPT-4.1-mini, Inference Strategy=SC2026.07 | 83.5 | |
| DCBackbone=GPT-4.1-mini, Inference Strategy=DC2026.07 | 83.5 | |
| BoTBackbone=GPT-4.1-mini, Inference Strategy=BoT2026.07 | 83 | |
| SCBackbone=GPT-4.1, Inference Strategy=SC2026.07 | 83 | |
| ZS-CoTBackbone=GPT-4.1-mini, Inference Strategy=ZS-CoT2026.07 | 82 | |
| ZS-CoTBackbone=GPT-4.1, Inference Strategy=ZS-CoT2026.07 | 81 | |
| DCBackbone=GPT-OSS-20B, Inference Strategy=DC2026.07 | 79 | |
| DCBackbone=GPT-4.1, Inference Strategy=DC2026.07 | 78 | |
| DCBackbone=Qwen3-30B-Instruct, Inference Strategy=DC2026.07 | 63.5 | |
| BoTBackbone=GPT-OSS-20B, Inference Strategy=BoT2026.07 | 42 |